Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1561
    Prev
    Next
    INDEX
    Explanations

    the word "there" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "there" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tamil
    -0.63
    icial
    -0.62
     Erit
    -0.57
    SEE
    -0.57
     cogn
    -0.56
     favour
    -0.56
    efe
    -0.56
     env
    -0.55
     ensemble
    -0.55
     Dish
    -0.55
    POSITIVE LOGITS
    abouts
    1.47
    upon
    1.23
    after
    0.91
    fore
    0.89
     ain
    0.84
    FORE
    0.77
     wasn
    0.77
     weren
    0.76
    'll
    0.76
     aren
    0.76
    Activations Density 0.131%

    No Known Activations